Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/therealtimex/browser-use/claude-mdgit clone --depth 1 https://github.com/therealtimex/browser-useWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02495 | $0.02495 |
| Opus 5 | $0.01247 | $0.01247 |
| Sonnet 5 | $0.00499 | $0.00499 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
browser-use CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to browser-use CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Browser-Use is an async python >= 3.11 library that implements AI browser driver abilities using LLMs + CDP (Chrome DevTools Protocol). The core architecture enables AI agents to autonomously navigate web pages, interact with elements, and complete complex tasks by processing HTML and making LLM-driven decisions.
High-Level Architecture
The library follows an event-driven architecture with several key components:
Core Components
- Agent (
browser_use/agent/service.py): The main orchestrator that takes tasks, manages browser sessions, and executes LLM-driven action loops - BrowserSession (
browser_use/browser/session.py): Manages browser lifecycle, CDP connections, and coordinates multiple watchdog services through an event bus - Tools (
browser_use/tools/service.py): Action registry that maps LLM decisions to browser operations (click, type, scroll, etc.) - DomService (
browser_use/dom/service.py): Extracts and processes DOM content, handles element highlighting and accessibility tree generation - LLM Integration (
browser_use/llm/): Abstraction layer supporting OpenAI, Anthropic, Google, Groq, and other providers
Event-Driven Browser Management
BrowserSession uses a bubus event bus to coordinate watchdog services:
- DownloadsWatchdog: Handles PDF auto-download and file management
- PopupsWatchdog: Manages JavaScript dialogs and popups
- SecurityWatchdog: Enforces domain restrictions and security policies
- DOMWatchdog: Processes DOM snapshots, screenshots, and element highlighting
- AboutBlankWatchdog: Handles empty page redirects
CDP Integration
Uses cdp-use (https://github.com/browser-use/cdp-use) for typed CDP protocol access. All CDP client management lives in browser_use/browser/session.py.
We want our library APIs to be ergonomic, intuitive, and hard to get wrong.
Development Commands
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 164 lines · 2,495 tokens per session scan A 8d6a85903545
browser-use CLAUDE.md is an instructions file published in the GitHub repository therealtimex/browser-use (0 stars, last pushed 11mo ago), licensed MIT. It adds 2,495 tokens to every session, about $0.0125 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to browser-use CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
deepseekCLI CLAUDE.md
Instructions for cynchro/deepseekCLI, covering tarea actual, progreso, decisiones clave, próximos pasos and contexto importante.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
agentoscope AGENTS.md
Instructions for rafaelcg/agentoscope, covering agentoscope — agent instructions, what this is, layout, commands and conventions.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).